Machine Learning Techniques PYQ 2023-24 AKTU (KAI601)

AKTU · BTECH · Semester 5, 6 · Machine Learning Techniques · Session 2023-24 · PYQ

AKTU Machine Learning Techniques (KAI601) previous year question paper 2023-24 for B.Tech Semester 5/6. Covers Introduction, Regression, Bayesian Learning…

Open the interactive reader to study this resource on AcademicArk.

Machine Learning Techniques AKTU syllabus

  1. Unit 1: Introduction
  2. Unit 2: Regression, Bayesian Learning and Support Vector Machine
  3. Unit 3: Decision Tree Learning and Instance-Based Learning
  4. Unit 4: Artificial Neural Networks and Deep Learning
  5. Unit 5: Reinforcement Learning and Genetic Algorithms

Questions in Machine Learning Techniques AKTU PYQ 2023-24

  1. Q1a. Name two types of learning commonly used in machine learning. (2 marks, 2023-24)
  2. Q1b. Give an example of a supervised learning problem. (2 marks, 2023-24)
  3. Q1c. What is logistic regression, and how does it differ from linear regression? (2 marks, 2023-24)
  4. Q1d. What are the three types of support vector kernels commonly used in SVMs? (2 marks, 2023-24)
  5. Q1e. Define inductive bias in the context of decision tree learning. (2 marks, 2023-24)
  6. Q1f. Describe the process of locally weighted regression in instance-based learning. (2 marks, 2023-24)
  7. Q1g. Define perceptron and their role in artificial neural networks. (2 marks, 2023-24)
  8. Q1h. What are the key characteristics of the Self-Organizing Map (SOM) algorithm? (2 marks, 2023-24)
  9. Q1i. Define Reinforcement Learning (RL) and explain its key components. (2 marks, 2023-24)
  10. Q1j. Discuss the components of a genetic algorithm. (2 marks, 2023-24)
  11. Q2a. Compare and contrast supervised, unsupervised, and reinforcement learning approaches in machine learning. (10 marks, 2023-24)
  12. Q2b. Discuss the mathematical formulation of linear regression, including the hypothesis function, cost function, and optimization algorithm used for parameter estimation. (10 marks, 2023-24)
  13. Q2c. Provide a detailed explanation of the ID3 algorithm used for constructing decision trees. Discuss the key steps involved in the iterative process of feature selection and node splitting. (10 marks, 2023-24)
  14. Q2d. Explain the fundamental concepts behind the Backpropagation Algorithm and its importance in training neural networks. (10 marks, 2023-24)
  15. Q2e. Explain the Q-learning algorithm and its role in Reinforcement Learning. (10 marks, 2023-24)
  16. Q3a. Discuss the role of Bayesian networks in representing probabilistic relationships between variables. Explain how Bayesian networks are constructed, updated, and utilized for inference in real-world scenarios. (10 marks, 2023-24)
  17. Q3b. Discuss the concept of model evaluation in machine learning. Compare and contrast evaluation metrics such as accuracy, precision, recall and F1-score. (10 marks, 2023-24)
  18. Q4a. Discuss the fundamental principles of the Expectation-Maximization (EM) algorithm and its role in probabilistic modeling and parameter estimation. (10 marks, 2023-24)
  19. Q4b. Define the concept of a hyperplane in the context of machine learning and Support Vector Machines (SVMs). Explain how hyperplanes are used as decision surfaces to separate classes in feature space. (10 marks, 2023-24)
  20. Q5a. Discuss how entropy measures the uncertainty or randomness of a dataset and its role in quantifying the impurity of decision tree nodes. (10 marks, 2023-24)
  21. Q5b. Describe the Locally Weighted Regression (LWR) technique and its purpose in machine learning. (10 marks, 2023-24)
  22. Q6a. Examine the effect of pooling layer parameters, such as pooling size and stride, on feature representation and network performance. (10 marks, 2023-24)
  23. Q6b. Describe the role of Convolutional Neural Networks (CNNs), in diagnosing Diabetic Retinopathy. (10 marks, 2023-24)
  24. Q7a. Critically analyze the strengths and limitations of Genetic Programming compared to other machine learning techniques. (10 marks, 2023-24)
  25. Q7b. Critically analyze the trade-offs between exploration and exploitation in the GA cycle of reproduction. (10 marks, 2023-24)

AKTU paper codes: BCS055, KCS055, BCDS062, KAI601

Machine Learning Techniques previous year papers

More Machine Learning Techniques resources

Browse all notes · Semester 5 notes